metadata
license: mit
language:
- ar
metrics:
- accuracy
- f1
- precision
- recall
library_name: transformers
tags:
- offensive language detection
base_model:
- UBC-NLP/MARBERT
This model is part of the work done in .
The full code can be found at https://github.com/wetey/cluster-errors
Model Details
Model Description
- Model type: BERT-based
- Language(s) (NLP): Arabic
- Finetuned from model: UBC-NLP/MARBERT
How to Get Started with the Model
Use the code below to get started with the model.
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-classification", model="wetey/MARBERT-LHSAB")
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("wetey/MARBERT-LHSAB")
model = AutoModelForSequenceClassification.from_pretrained("wetey/MARBERT-LHSAB")
Fine-tuning Details
Fine-tuning Data
This model is fine-tuned on the L-HSAB. The exact version we use (after removing duplicates) can be found .
Fine-tuning Procedure
The exact fine-tuning procedure followed can be found here
Training Hyperparameters
evaluation_strategy = 'epoch'
logging_steps = 1,
num_train_epochs = 5,
learning_rate = 1e-5,
eval_accumulation_steps = 2
Evaluation
Testing Data
Test set used can be found here
Results
accuracy: 87.9%
precision: 88.1%
recall: 87.9%
f1-score: 87.9%
Results per class
| Label | Precision | Recall | F1-score |
|---|---|---|---|
| normal | 85% | 82% | 83% |
| abusive | 93% | 92% | 93% |
| hate | 68% | 78% | 72% |